© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11819
    Prev
    Next
    INDEX
    Explanations

    better to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     啊
    3.81
     可以
    3.75
     哦
    3.69
     render
    3.48
     你
    3.45
     也
    3.45
     很
    3.44
     情况
    3.28
     不能
    3.26
     但是
    3.24
    POSITIVE LOGITS
    ing
    3.30
    tidak
    3.29
    टेगरी
    3.06
    स्ताना
    3.00
    going
    2.83
    não
    2.83
    adinam
    2.77
    untuk
    2.76
    प
    2.76
    ায়ত্ত
    2.74
    Activations Density 0.041%

    No Known Activations